© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69538
    Prev
    Next
    INDEX
    Explanations

    Pregnancy, roleplay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     деш
    -0.10
     공격
    -0.09
     행동
    -0.09
     실행
    -0.09
     Apache
    -0.09
     explo
    -0.09
     ആക്രമ
    -0.09
     резко
    -0.09
     criminals
    -0.09
     exécut
    -0.08
    POSITIVE LOGITS
     breastfeeding
    0.13
     Schwangerschaft
    0.13
     postpartum
    0.13
     pregnancy
    0.12
     motherhood
    0.11
     pregnancies
    0.11
     wedding
    0.11
     zwangers
    0.11
     childbirth
    0.11
     mothers
    0.11
    Activations Density 0.088%

    No Known Activations